Multiclass Arrhythmia Classification using Smartwatch Photoplethysmography Signals Collected in Real-life Settings

TL;DR

This study develops a multimodal smartwatch-based deep learning model that significantly improves arrhythmia detection sensitivity, especially for PAC/PVC, using real-world data and efficient computation.

Contribution

Introduces a multimodal 1D-Bi-GRU model that outperforms existing methods in arrhythmia detection using smartwatch data from real-life settings.

Findings

Achieved 83% sensitivity for PAC/PVC detection.

Maintained 97.31% accuracy for AF detection.

Model is 14 times lighter and 2.7 times faster than previous models.

Abstract

Most deep learning models of multiclass arrhythmia classification are tested on fingertip photoplethysmographic (PPG) data, which has higher signal-to-noise ratios compared to smartwatch-derived PPG, and the best reported sensitivity value for premature atrial/ventricular contraction (PAC/PVC) detection is only 75%. To improve upon PAC/PVC detection sensitivity while maintaining high AF detection, we use multi-modal data which incorporates 1D PPG, accelerometers, and heart rate data as the inputs to a computationally efficient 1D bi-directional Gated Recurrent Unit (1D-Bi-GRU) model to detect three arrhythmia classes. We used motion-artifact prone smartwatch PPG data from the NIH-funded Pulsewatch clinical trial. Our multimodal model tested on 72 subjects achieved an unprecedented 83% sensitivity for PAC/PVC detection while maintaining a high accuracy of 97.31% for AF detection. These results outperformed the best state-of-the-art model by 20.81% for PAC/PVC and 2.55% for AF detection even while our model was computationally more efficient (14 times lighter and 2.7 faster).